All Issue

2024 Vol.29, Issue 2 Preview Page

Article

Development and Assessment of LSTM Model for Correcting Underestimation of Water Temperature in Korean Marine Heatwave Prediction System

한반도 고수온 예측 시스템의 수온 과소모의 보정을 위한 LSTM 모델 구축 및 예측성 평가

NA KYOUNG IM1
,
HYUNKEUN JIN2
,
GYUNDO PAK3
,
YOUNG-GYU PARK4
,
KYEONG OK KIM4
,
YONGHAN CHOI5
,
YOUNG HO KIM6*
임 나경1
,
진 현근2
,
박 균도3
,
박 영규4
,
김 경옥4
,
최 용한5
,
김 영호6*
1Undergraduate Student, Division of Earth Environmental System Science, Pukyong National University, Busan 48513, Korea
2Full-time Research Specialist, Ocean Circulation & Climate Research Department, Korea Institute of Ocean Science & Technology, Busan 49111, Korea
3Senior Research Scientist, Ocean Circulation & Climate Research Department, Korea Institute of Ocean Science & Technology, Busan 49111, Korea
4Principal Research Scientist, Ocean Circulation & Climate Research Department, Korea Institute of Ocean Science & Technology, Busan 49111, Korea
5Senior Research Scientist, Korea Polar Research Institute, Division of Ocean & Atmosphere Sciences, Incheon 21990, Korea
6Assistant Professor, Division of Earth Environmental System Science, Pukyong National University, Busan 48513, Korea
1국립부경대학교 지구환경시스템과학부 해양학전공 학부생
2한국해양과학기술원 해양순환기후연구부 무기계약직기술원
3한국해양과학기술원 해양순환기후연구부 선임연구원
4한국해양과학기술원 해양순환기후연구부 책임연구원
5극지연구소 해양대기연구본부 선임연구원
6국립부경대학교 지구환경시스템과학부 해양학전공 조교수
*Corresponding Author
31 May 2024. pp. 101-115
PDF XML Citation
Abstract

The ocean heatwave is emerging as a major issue due to global warming, posing a direct threat to marine ecosystems and humanity through decreased food resources and reduced carbon absorption capacity of the oceans. Consequently, the prediction of ocean heatwaves in the vicinity of the Korean Peninsula is becoming increasingly important for marine environmental monitoring and management. In this study, an LSTM model was developed to improve the underestimated prediction of ocean heatwaves caused by the coarse vertical grid system of the Korean Peninsula Ocean Prediction System. Based on the results of ocean heatwave predictions for the Korean Peninsula conducted in 2023, as well as those generated by the LSTM model, the performance of heatwave predictions in the East Sea, Yellow Sea, and South Sea areas surrounding the Korean Peninsula was evaluated. The LSTM model developed in this study significantly improved the prediction performance of sea surface temperatures during periods of temperature increase in all three regions. However, its effectiveness in improving prediction performance during periods of temperature decrease or before temperature rise initiation was limited. This demonstrates the potential of the LSTM model to address the underestimated prediction of ocean heatwaves caused by the coarse vertical grid system during periods of enhanced stratification. It is anticipated that the utility of data-driven artificial intelligence models will expand in the future to improve the prediction performance of dynamical models or even replace them.

Keywords
Marine heatwave
Machine learning
Artificial intelligence
LSTM

해양의 고수온 현상은 지구온난화로 인한 주요 문제 중 하나로, 식량 자원의 감소와 해양 탄소 흡수력의 저하 등, 해양 생태계와 인류에게 직접적인 위협으로 부상하고 있다. 따라서, 한반도 주변 해역에서의 고수온 예측은 해양 환경 모니터링 및 관리에 중요하다. 본 연구에서는 역학 모델 기반 한반도 고수온 예측 시스템의 성긴 해양의 수직격자체계로 인한 고수온 예측의 과소모의를 개선하기 위해 LSTM 모델을 개발하였다. 2023년에 대해 수행된 한반도 고수온 예측 시스템의 고수온 예측 결과와 LSTM 모델의 결과를 기반으로 한반도 주변의 동해 해역, 황해 해역 그리고 남해 해역에서의 고수온 예측 성능을 평가했다. 본 연구에서 개발된 LSTM 모델이 세 영역 모두에서 수온이 상승하는 시기에 수온 예측 성능을 크게 개선하는 것으로 나타났으며, 수온 상승이 시작되기 전이나 하강하는 시기에는 예측 성능의 개선 효과가 미미했다. 이는 LSTM 모델이 성층이 강화되는 환경에서 성긴 수직격자로 인해 발생하는 고수온 예측의 과소모의를 개선할 수 있는 가능성을 보여준다. 향후 역학 모델의 예측 성능 개선이나 역학 모델의 대체에 자료 기반 인공지능 모델의 활용성이 확대될 것으로 기대한다.

References
1

Ahn, J., I. Park, S. Lyu and Y. Hur, 2012. Evaluation of Optimal Grid Resolution for Hydrodynamic Proper Simulation. Journal of Korean Society for Geospatial Information Science, 20(1): 109-116. DOI: 10.7319/kogsis.2012.20.1.109.

10.7319/kogsis.2012.20.1.109
2

EU Copernicus Marine Environment Monitoring Service (CMEMS), 2023. PRODUCT USER MANUAL For the Global Ocean Physical Multi Year product GLOBAL_MULTIYEAR_PHY_001_030, EU Copernicus Marine Service - Public, no.1.5, DOI: 10.48670/moi-00021.

3

Han, I. and J. Lee, 2020. Change the Annual Amplitude of Sea Surface Temperature due to Climate Change in a Recent Decade around the Korean Peninsula. Journal of the Korean Society of Marine Environment & Safety, 26(3): 233-241. DOI: 10.7837/kosomes.2020.26.3.233.

10.7837/kosomes.2020.26.3.233
4

Han, I., J. Lee, C. Kim and J. Yaong, 2023. Impacts, projections and assessments related to climate change in ocean and fisheries. Journal of Climate Change Research, 14(6-2): 965-972: DOI: 10.15531/KSCCR.2023.14.6.965.

10.15531/KSCCR.2023.14.6.965
5

Hersbach, H., B. Bell, P. Berrisford, G. Biavati, A. Horányi, J. Muñoz Sabater, J. Nicolas, C. Peubey, R. Radu, I. Rozum, D. Schepers, A. Simmons, C. Soci, D. Dee and J.-N. Thépaut, 2023. ERA5 hourly data on single levels from 1940 to present, Copernicus Climate Change Service (C3S) Climate Data Store (CDS), DOI: 10.24381/cds.adbb2d47.

6

Hochreiter, S. and J. Schmidhuber, 1997. Long short-term memory. Neural computation, 9(8): 1735-1780. DOI: 10.1162/neco.1997.9.8.1735.

10.1162/neco.1997.9.8.17359377276
7

Hu, H., A. Westhuysen, P. Chu and A. Fujisaki-Manome, 2021. Predicting Lake Erie wave heights and periods using XGBoost and LSTM. Ocean Modelling, 164. DOI: 10.1016/j.ocemod.2021.101832.

10.1016/j.ocemod.2021.101832
8

Huang, B., Z. Wang, X. Yin, A. Arguez, G. Graham, C. Liu, T. Smith and H. Zhang, 2021. Prolonged Marine Heatwaves in the Arctic: 1982-2020. Geophysical Research Letters, 48(24). DOI: 10.1029/2021GL095590.

10.1029/2021GL095590
9

Jeong, H., S. Lee, Y. Lee and Y. Seo, 2023. Development of bias correction model for downward short wave radiation in South Korea using high-resolution numerical model prediction information. Journal of Korean Institute of Intelligent Systems, 33(2): 162-172. DOI: 10.5391/JKIIS.2023.33.2.162.

10.5391/JKIIS.2023.33.2.162
10

Kim, M., H. Choi and H. Yang, 2021. Method for Improving Sea Surface Temperature and High Water Temperature Prediction Performance using LSTM. Korean Institute of Information Scientists and Engineers, 744-746.

11

Kingma, D. and J. Ba, 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, DOI: 10.48550/arXiv.1412.6980.

12

Korea Institute of Ocean Science & Technology (KIOST). 2024. Investigation and prediction system development of marine heatwave aroundthe Korean Peninsula originated from the subarctic and western Pacific, 696 pp.

13

Korea Meteorological Administration (KMA), 2018. Abnormal climate report 2018, Korea Meteorological Administration.

14

Lee, K., I. Zo, J. Jee and Y. Choi, 2011. Temporal and Spatial Distributions of the Surface Solar Radiation by Spatial Resolutions on Korea Peninsula. New & Renewable Energy, 7(1): 22-28. DOI: 10.7849/ksnre.2011.7.1.022.

10.7849/ksnre.2011.7.1.022
15

Lee, K., M. Kwon and H. Kang, 2022. Record-breaking High Temperature in July 2021 over East Sea and Possible Mechanism. Atmosphere, 32(1): 17-25. DOI: 10.14191/Atmos.2022.32.1.017.

16

Lee, S., M. Park, M. Kwon, Y. Kim and Y. Park, 2020. Two major modes of East Asian marine heatwaves. Environmental Research Letters, 15(7). DOI: 10.1088/1748-9326/ab8527.

10.1088/1748-9326/ab8527
17

Lee, S., M. Park, M. Kwon, Y. Park, Y. Kim and N. Choi, 2023. Rapidly changing East Asian marine heatwaves under a warming climate. Journal of Geophysical Research - Oceans, 128(6). DOI: 10.1029/2023JC019761.

10.1029/2023JC019761
18

Oh, H., G. Kim, J. Chu, K. Lee and J. Jeong, 2023. The record-breaking 2022 long-lasting marine heatwaves in the East China Sea. Environmental Research Letters, 18(6). DOI: 10.1088/1748-9326/acd267.

10.1088/1748-9326/acd267
19

Oliver, E., M. Donat, M. Burrows, P. Moore, D. Smale, L. Alexander, J. Benthuysen, M. Feng, A. Gupta, A. Hobday, N. Holbrook, S. Perkins-Kirkpatrick, H. Scannell, S. Straub and T. Wernberg, 2018. Longer and more frequent marine heatwaves over the past century. Nature Communications, 9(1): 1-12.

10.1038/s41467-018-03732-929636482PMC5893591
20

Siami-Namin, S., N. Tavakoli and A.S. Namin, 2018. A Comparison of ARIMA and LSTM in Forecasting Time Series, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), 1394-1401, DOI: 10.1109/ICMLA.2018.00227.

10.1109/ICMLA.2018.00227
21

Tan, H., R. Cai and R. Wu, 2022. Summer marine heatwaves in the South China Sea: Trend, variability and possible causes. Advances in Climate Change Research, 13(3): 323-332. DOI: 10.1016/j.accre.2022.04.003.

10.1016/j.accre.2022.04.003
22

Zhang, Q., H. Wang, J. Dong, G. Zhong and X. Sun, 2017. Prediction of sea surface temperature using long short-term memory. IEEE geoscience and remote sensing letters, 14(10): 1745-1749: DOI: 10.1109/LGRS.2017.2733548.

10.1109/LGRS.2017.2733548
Information
  • Publisher :The Korean Society of Oceanography
  • Publisher(Ko) :한국해양학회
  • Journal Title :The Sea Journal of the Korean Society of Oceanography
  • Journal Title(Ko) :한국해양학회지 바다
  • Volume : 29
  • No :2
  • Pages :101-115
  • Received Date : 2024-04-16
  • Revised Date : 2024-05-28
  • Accepted Date : 2024-05-29
  • DOI :https://doi.org/10.7850/jkso.2024.29.2.101
Journal Informaiton The Sea Journal of the Korean Society of Oceanography The Sea Journal of the Korean Society of Oceanography
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close